Show Tag: rnnpb

Select Other Tags

Kleesiek et al. use a recurrent neural network with parametric bias (RNNPB) to classify objects from the multisensory percepts induced by interacting with them.

Kleesiek et al. introduce adaptive learning rates to RNNPB which results in faster and more stable training.

RNNPB learns sequences of inputs unsupervised (self-organized).

Similar parametric bias vectors are learned by the RNNPB for similar input.